© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28048
    Prev
    Next
    INDEX
    Explanations

    simply distinguish listing leap special

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    नेश्वर
    0.43
     основным
    0.40
    новні
    0.39
    onis
    0.38
    Initialization
    0.38
    リーズ
    0.38
    Wake
    0.38
    沨
    0.37
    ጧ
    0.36
     pertinent
    0.36
    POSITIVE LOGITS
    蒴
    0.48
     ثم
    0.45
     selanjutnya
    0.45
     uiteindelijk
    0.44
     lalu
    0.44
     finalmente
    0.43
     עי
    0.43
     kamen
    0.43
     khal
    0.43
     kemudian
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.